INDEX

Explanations

numeric values, particularly those related to contact information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

specific numbers or sequences

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.55

ArgsConstructor

-0.51

VersionUID

-0.46

IsContent

-0.46

+#+#

-0.43

ConstraintMaker

-0.42

#+#

-0.42

outSlope

-0.42

SpringRunner

-0.41

numerusform

-0.41

POSITIVE LOGITS

OGND

0.51

 समीक्षाओं

0.44

Personensuche

0.43

Rüyada

0.42

 resident

0.42

횟

0.41

AddHtmlAttribute

0.40

팎

0.38

Viitteet

0.38

 residente

0.38

Activations Density 0.000%

numeric values, particularly those related to contact information

specific numbers or sequences

No Comments

No Known Activations